Metraipolis › archive › dc_f3efd2b98372

Vulnerabilities in Personalization: Assessing Health Privacy Risks in ChatGPT Logs and Memory — arXiv:2609.14697

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14697
License (as archived)
CC0-1.0
Archived
2026-10-15T23:48:04.775Z
SHA-256 of the archived text
614e5bd144606db32c1ed4e6ee90d80f967b939db40535f6610747d6c38c1841
Stable URL of this page
https://metraipolis.com/documento/dc_f3efd2b98372

How to cite

Vulnerabilities in Personalization: Assessing Health Privacy Risks in ChatGPT Logs and Memory — arXiv:2609.14697 — arXiv (en), https://arxiv.org/abs/2609.14697 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3efd2b98372 (Metraipolis archive dc_f3efd2b98372, sha256 614e5bd144606db32c1ed4e6ee90d80f967b939db40535f6610747d6c38c1841)
BibTeX
@misc{dcf3efd2b98372,
  title = {Vulnerabilities in Personalization: Assessing Health Privacy Risks in ChatGPT Logs and Memory — arXiv:2609.14697},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14697},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3efd2b98372; sha256 614e5bd144606db32c1ed4e6ee90d80f967b939db40535f6610747d6c38c1841},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14697. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As conversational LLMs become deeply embedded in daily life, users frequently disclose sensitive personal health information during routine interactions. We present a large-scale computational audit analyzing 179,057 conversations across India, Nigeria, Brazil, and Pakistan (N = 1,057) to evaluate personal health disclosures and background memory synthesis in ChatGPT. We find that 21.31% of audited conversations contain personal health data, with 3.62% posing high-to-extreme privacy risks involving stigmatized conditions, direct identifiers, and precise locations. When evaluating the memory entries of ChatGPT, we uncover a stark disconnect between corporate framing and system behavior: over 95% of profile entries are implicitly extracted without explicit user prompts or consent. Furthermore, background memory synthesis selectively condenses temporary, symptom-level disclosures into permanent diagnostic traits, stripping contextual integrity and amplifying re-identification risks. We conclude with sociotechnical design guidelines to restore user agency and consent-driven boundaries in stateful AI systems.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CY).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2609.14697 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T23:17:38.176Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).